INDEX
    Explanations

    Determiner before nouns

    New Auto-Interp
    Negative Logits
    0.98
    an
    0.60
    z
    0.59
    ل
    0.58
    in
    0.54
    و
    0.49
    f
    0.47
    7
    0.46
    8
    0.46
    ان
    0.45
    POSITIVE LOGITS
     to
    0.79
     at
    0.54
     is
    0.48
     
    0.45
     of
    0.43
     was
    0.43
     that
    0.42
     a
    0.41
     be
    0.41
    0.41
    Act Density 1.433%

    No Known Activations